Choose the right instance for inference deployment with SageMaker Inference Recommender

Amazon SageMaker Inference Recommender speeds up the process of finding the right compute instance type for your model deployment that gives you the highest performance at the lowest cost by automatically running performance benchmarking and tuning model performance across SageMaker ML instances. In this video we dive deep into how SageMaker Inference Recommender works and how you can use it to select the right instance for your inference deployments. Code examples: https://github.com/shashankprasanna/s... reinvent summary blog post: https://towardsdatascience.com/aws-re...